US20130204833A1 - Personalized recommendation of user comments - Google Patents
Personalized recommendation of user comments Download PDFInfo
- Publication number
- US20130204833A1 US20130204833A1 US13/364,369 US201213364369A US2013204833A1 US 20130204833 A1 US20130204833 A1 US 20130204833A1 US 201213364369 A US201213364369 A US 201213364369A US 2013204833 A1 US2013204833 A1 US 2013204833A1
- Authority
- US
- United States
- Prior art keywords
- user
- comments
- generated
- interest
- generated comments
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
Definitions
- the present invention relates to services that allow users to comment on items and, more specifically, to techniques for helping each user to consume the user comments in which the user is personally interested.
- User-generated opinions take many forms. For example, one common form of user-generated opinions is user reviews. It is common for popular items to receive an unmanageably large number of user reviews. For example, on a book-selling website, a best-selling book may receive over 1000 reviews. Similarly, on a service that allows users to review restaurants, a popular restaurant can garner over 1000 reviews.
- news articles on popular topics may receive an unwieldy number of comments. For example, during the short period of time for which a major event is active, news stories on one single event can easily attract over ten thousand comments on popular online news sites.
- user-generated comments refers to any content, provided by users for online publication, in relation to subject matter that is published or being discussed online.
- the subject matter at which the user-generated comments are directed may include, but is not limited to, products, songs, movies, news articles, discussion topics, sports teams, services, etc.
- user-generated comments are published in conjunction with the subject matter to which the user-generated comments relate (the “target subject matter”).
- the same webpage that has a news article may also include user comments related to the news article.
- user-generated comments often do not actually express opinions about the target subject matter.
- a user comment entered in relation to a news article may not actually have anything to do with the topic of the news article.
- Review summarization may involve, for example, (a) automatically or manually identifying ratable aspects, and (b) presenting overall sentiment polarity for each aspect.
- Another technique for assisting user consumption of user-generated comments involves predicting the overall helpfulness of reviews in the hope of promoting those with better quality, where helpfulness is usually defined as some function over the percentage of users who found the review to be helpful. Both summarization and using a helpfulness rating focus on distilling subjective information that may be interesting to an average user.
- FIG. 1 is a block diagram that illustrates how comments for the same article are presented in a different manner to three different users, according to an embodiment of the invention.
- FIG. 2 is a block diagram of a computer system upon which embodiments of the invention may be implemented.
- Techniques are described herein for facilitating the consumption of user-generated comments by determining which comments will be of most interest to each individual user. Once the comments that will be of most interest to a particular user are determined, the user-generated comments are presented to that user in a manner that reflects that user's predicted interest. For example, from 1000 reviews of a movie, each user may be presented with the 20 reviews that are predicted to be of most interest to the user. Because the predictions are personalized, different users are presented with different sets of 20 reviews, all for the same movie.
- all users may be presented the same 1000 reviews, but the reviews may be ordered based on predictions of how interested each individual user would be in each review.
- the per-individual interest predictions may affect the display of user-generated comments in other ways, such as showing the reviews that are predicted to be of higher interest in different colors, highlighting, or using a larger font size.
- the layout of the interface presented to a user may also reflect user-specific information. For example, a user that is a frequent commenter may be provided an interface with a more prominent control for submitting comments, while a user that tends to skim through comments may be provided an interface that includes a greater number of comments.
- summarization of comments is also performed based on user-specific interest scores. For example, a user may be presented with summaries or aggregate ratings of only those comments that exceed a certain threshold of interest score for the user. Similarly, summaries may be separately derived and displayed for comments with interest scores above a threshold, and for comments with interest scores below the threshold. Those comments that are selected for display to a user may also include a first set of comments that are selected because they have high interest scores, and another set that are selected because they have low interest scores.
- interest predictions for a user may be based on the user's prior rating of comments, the ratings made by other users that are similar to the user, the textual content of comments, the textual content of the target subject matter, user-generated tags that have been supplied for the target subject matter, user-generated tags that have been supplied for comments, the degree to which comments are related to the subjects which they target, various types of profile and/or demographic information about the user, the user's social network connections, the authors of the comments, the author of the target subject matter, the user's propensity to comment, etc.
- a system for recommending user-generated comments to users in a user-specific manner.
- many user-generated comment environments allow user to mark “like” or “dislike” over existing user-generated comments.
- a recommendation system may learn from each user's past preferences so that when a user is reading a news article, the user-generated comments for that article may be automatically ranked according to the likelihood of them being liked by this user.
- Such a system may be used directly to create personalized presentation of user-generated comments, as well as enabling down-stream applications, such as personalized summarization.
- FIG. 1 it illustrates displays that may result by implementing a personalized comment recommendation system, according to an embodiment of the invention.
- a comment recommendation engine (not shown) determines user-specific interest scores for the comments associated with the article. Based on the user-specific interest scores, the comment recommendation engine determines which comments should be included on the webpage that is returned to each of the three users, and the order in which the comments are presented.
- the same comments were selected for user 1 and user 2 , but the order in which the comments are presented differs based on the differences in the interest scores that those comments produced relative to user 1 and user 2 .
- the comments that are selected and displayed to user 3 include many comments that were not displayed to user 1 and user 2 , and are missing some of the comments that were displayed to user 1 and user 2 .
- FIG. 1 is merely one example of how the display of comments, from the comment pool of the same target subject matter, may differ from user to user based on user-specific interest scores generated for the comments.
- the difference in interest scores of the comments may be reflected in other ways, such as the font size of the comments, the color of the comments, the amount of text shown in the initial display of the comments (where more text is initially shown for comments that are predicted to be of higher interest), etc.
- a recommendation system for user-generated comments differs in a variety of ways from a system that recommends target subject matter, such as articles, to users. Specifically, recommending articles is largely about identifying the topics of interest to a given user, and it is conceivable that unigram representation of full-length articles can reasonably capture that information. In contrast, most user-generated comments for an article a user is reading are already of interest to that user topically. Which ones the user like may depend on several non-topical aspects of the text, such as: whether the user agrees with the viewpoint expressed in the user-generated comment, whether the user-generated comment is convincing and well-written, etc. In addition, user-generated comments are typically much shorter than full length articles, so there is generally less content upon which to base any recommendations.
- the difficulty in analyzing the textual information in user-generated comments can be alleviated by taking into account additional contextual information, such as author identities. If between a pair of users, one consistently likes or dislikes the other, then at least for the heavy users, this authorship information in itself could be adequate basis to determine whether a particular comment provided by one of the users would be of interest to the other user.
- multiple sources of information are used for the task of recommending user-generated comments.
- authorship information is used in addition to textual information. Examples of various sources, and how information from those sources may be used to generate per-user interest scores for user-generated comments, are provided in greater detail hereafter.
- one factor used to automatically determine personalized interest scores is rater affinity to the user-generated comments.
- rater affinity is determined using a model that incorporates rater-comment interactions and rater-author interactions simultaneously in a principled fashion.
- the model also provides a seamless mechanism to transition from cold-start (where recommendations need to be made for users or items with no or few past ratings) to warm-start scenarios—with a large amount of data, it fits a per-rater (author) model; with increase in data sparsity, the model applies a small sample size correction through features (e.g. textual features).
- the exact formula for such corrections in the presence of sparsity is based on parameter estimates that are obtained by applying an EM algorithm to the training data.
- a model is described herein for generating personalized interest scores for user-generated comments, according to an embodiment of the invention.
- This model is merely one example of how personalized interest scores may be generated, and the techniques described herein are not limited to any particular model, not any particular set of factors used by the model.
- y ij denotes the rating that user i, called the rater, gives to user-generated comment j.
- suffix i is used to denote a rater and suffix j to denote a user-generated comment
- x i (of dimension p u ) and x j (of dimension p c ) denote feature vectors of user i and user-generated comment j, respectively.
- x i can be the bag of words representation (a sparse vector) inferred through text analysis on user-generated comments voted positively by user i in the past
- x j can be the bag of words representation for user-generated comment j.
- ⁇ ij cannot be estimated empirically since each user i usually rates a user-generated comment j at most once.
- ⁇ ij (or some monotone function h of ⁇ ij ) is an additive function of:
- one embodiment includes terms that capture interactions among entities (raters, authors, user-generated comments).
- latent factors are attached to each rater, author and user-generated comment. These latent factors are finite dimensional Euclidean vectors that are unknown and estimated from the data. They provide a succinct representation of various aspects that are important to explain interaction among entities. In one embodiment, the following factors are used:
- Affinity of rater i to user-generated comment j by author a(j) is captured by:
- Equation 1 This equation shall be referred to hereafter as Equation 1.
- h ⁇ ( ⁇ ij ) log ⁇ ⁇ ⁇ ij 1 - ⁇ ij
- Latent factors To estimate latent factors in Equation 1, a maximum likelihood estimation (MLE) approach does not work well because a large fraction of entities have small sample size. For instance, if a user-generated comment is rated only by one user and r u >1, then the model is clearly overparametrized and the MLE of the user-generated comment factor would tend to learn idiosyncrasies in the training data.
- MLE maximum likelihood estimation
- constraints are imposed on the factors to obtain estimates that generalize well on unseen data.
- a Bayesian framework may be used, where such constraints are imposed through prior distributions.
- g p u ⁇ 1 and d p u ⁇ 1 are regression weight vectors
- u i will be predicted as the prior mean (backoff) Gx i , a linear projection from the feature vector x i through matrix G learnt from data. This projection can be thought of as a multivariate linear regression problem with weight matrix G, one weight vector per dimension of u i .
- the per-user residual i that is not captured by the regression Gx i is estimated. For sample sizes in between these two extremes, the per user residual estimate is “shrunk” toward zero, where the amount of shrinkage depends on the sample size, past user ratings, variability in ratings on user-generated comments rated by the user, and the value of variance components ⁇ 2 ⁇ s .
- the full model (vv+uc) includes several existing models explored in collaborative filtering and social networks as special cases.
- the uc model This is also a matrix factorization model but with priors based on regressions (i.e., non-zero g; d; G; D). It provides a mechanism to deal with both cold and warm-start scenarios in recommender applications (Agarwal and Chen (2009)).
- x′ i G′Dx j can be written as x′ i Ax j , where is the matrix of regression weights (Chu and Park, 2009).
- A can be a large matrix that needs to be learnt from data.
- A G′D, where the number of rows in D and G are small.
- model fitting for the example model described above is based on the expectation-maximization (EM) algorithm (Dempster et al., 1977).
- EM expectation-maximization
- a sketch of the algorithm for the Gaussian case is provided.
- the logistic model can be fitted along the same lines by using a variational approximation (see Agarwal and Chen (2009)).
- ⁇ (t) denote the estimated parameter setting at the t th iteration.
- the EM algorithm iterates through the following two steps until convergence.
- ⁇ is the input variable of function f t , but ⁇ (t) consists of known quantities (determined in the previous iteration).
- M-step Find the ⁇ that maximizes the expectation computed in the E-step.
- ⁇ ( t + 1 ) arg ⁇ ⁇ max ⁇ ⁇ f t ⁇ ( ⁇ )
- a Gibbs sampler is used to compute the Monte Carlo expectation (Booth and Hobert, 1999).
- the Gibbs sampler repeats the following procedure L times. It samples ⁇ i , ⁇ i , ⁇ j , u i , v j and c j sequentially one at a time by sampling from the corresponding full conditional distributions.
- the full conditional distributions are all Gaussian, hence they are easy to sample.
- the optimization of variance components ⁇ 2 s in the M-step is available in closed form, the regression parameters are estimated through off-the-shelf linear regression routines.
- the posterior distribution of latent factors for known ⁇ is multi-modal, and the Monte Carlo based EM method tends to outperform other optimization methods like gradient descent in terms of predictive accuracy.
- the example model described above may be applied in many contexts to generate per-user-per-comment interest scores, and to present user-generated comments in a manner that is based on those interest scores.
- the model may be applied in a situation where users read and comment on articles (such as news articles, blogs posts, status updates, event announcements, etc.), and have a mechanism for rating the comments.
- Information about how users actually rated the comments may be collected and used as a training set. Specifically, a portion of the collected data may be used for training, a portion for tuning, and a portion for testing the accuracy of the model.
- all comments may be tokenized, lower-cased, with stopwords and punctuations removed. Further, the tokens may be filtered so that only the N most frequently used tokens are considered (where N may be, for example, 10,000). According to one embodiment, a rater feature vector is created by summing over the feature vectors of all comments rated positively by the rater.
- Various methods may be used to apply the example model to produce per-user-per-comment interest scores.
- various embodiments may use any one or any combination of the full model vv+uc, as well as the three main special cases, vv, uc, and bilinear.
- the dimensions of v i , u i and c j (i.e., r v and r u ), and the rank of bilinear are selected to obtain the best AUC on the tuning set.
- the following baseline methods may be used to predict per-user preferences in isolation, primarily based on textual information.
- Cosine similarity (cos): x′ i x j . This is simply based on how similar a new comment j is to the comments rater i has liked in the past.
- Per-user SVM For each rater, train a support vector machine (SVM) classifier using only comments (x j ) rated by that user.
- SVM support vector machine
- Per-user Naive Bayes For each rater, train a Naive Bayes classifier using only comments (x j ) rated by that user.
- SVMs typically yield the best performance on text classification tasks.
- a Naive Bayes classifier can be more robust over shorter text spans common in user comments given the high variance.
- the example model described above uses various factors to determine per-user-per-comment interest scores.
- the factors used by the example model are merely some of the virtually limitless factors that may be used to determine how interested a specific user would be in each specific user-generated comment.
- a non-exhaustive list of factors that may be used individually or in any combination to determine individualized interest scores for user-generated comments for a particular reader includes:
- the particular user is provided a presentation of the user-generated comments that is personalized based on the interest scores.
- the number of ways the presentation can be personalized based on the interest scores is virtually endless. Two relatively simple forms of personalization include selecting which comments to show based on the interest scores, and determining the ranking of the comments based on the interest scores. However, there are any number of other ways the display of the comments may be personalized instead of or in addition to selection and ranking. Examples of ways to personalize the presentation of comments include:
- the techniques described herein are implemented by one or more special-purpose computing devices.
- the special-purpose computing devices may be hard-wired to perform the techniques, or may include digital electronic devices such as one or more application-specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that are persistently programmed to perform the techniques, or may include one or more general purpose hardware processors programmed to perform the techniques pursuant to program instructions in firmware, memory, other storage, or a combination.
- ASICs application-specific integrated circuits
- FPGAs field programmable gate arrays
- Such special-purpose computing devices may also combine custom hard-wired logic, ASICs, or FPGAs with custom programming to accomplish the techniques.
- the special-purpose computing devices may be desktop computer systems, portable computer systems, handheld devices, networking devices or any other device that incorporates hard-wired and/or program logic to implement the techniques.
- FIG. 2 is a block diagram that illustrates a computer system 200 upon which an embodiment of the invention may be implemented.
- Computer system 200 includes a bus 202 or other communication mechanism for communicating information, and a hardware processor 204 coupled with bus 202 for processing information.
- Hardware processor 204 may be, for example, a general purpose microprocessor.
- Computer system 200 also includes a main memory 206 , such as a random access memory (RAM) or other dynamic storage device, coupled to bus 202 for storing information and instructions to be executed by processor 204 .
- Main memory 206 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 204 .
- Such instructions when stored in non-transitory storage media accessible to processor 204 , render computer system 200 into a special-purpose machine that is customized to perform the operations specified in the instructions.
- Computer system 200 further includes a read only memory (ROM) 208 or other static storage device coupled to bus 202 for storing static information and instructions for processor 204 .
- ROM read only memory
- a storage device 210 such as a magnetic disk or optical disk, is provided and coupled to bus 202 for storing information and instructions.
- Computer system 200 may be coupled via bus 202 to a display 212 , such as a cathode ray tube (CRT), for displaying information to a computer user.
- a display 212 such as a cathode ray tube (CRT)
- An input device 214 is coupled to bus 202 for communicating information and command selections to processor 204 .
- cursor control 216 is Another type of user input device
- cursor control 216 such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 204 and for controlling cursor movement on display 212 .
- This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the device to specify positions in a plane.
- Computer system 200 may implement the techniques described herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware and/or program logic which in combination with the computer system causes or programs computer system 200 to be a special-purpose machine. According to one embodiment, the techniques herein are performed by computer system 200 in response to processor 204 executing one or more sequences of one or more instructions contained in main memory 206 . Such instructions may be read into main memory 206 from another storage medium, such as storage device 210 . Execution of the sequences of instructions contained in main memory 206 causes processor 204 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions.
- Non-volatile media includes, for example, optical or magnetic disks, such as storage device 210 .
- Volatile media includes dynamic memory, such as main memory 206 .
- Common forms of storage media include, for example, a floppy disk, a flexible disk, hard disk, solid state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge.
- Storage media is distinct from but may be used in conjunction with transmission media.
- Transmission media participates in transferring information between storage media.
- transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise bus 202 .
- transmission media can also take the form of acoustic or light waves, such as those generated during radio-wave and infra-red data communications.
- Various forms of media may be involved in carrying one or more sequences of one or more instructions to processor 204 for execution.
- the instructions may initially be carried on a magnetic disk or solid state drive of a remote computer.
- the remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem.
- a modem local to computer system 200 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal.
- An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data on bus 202 .
- Bus 202 carries the data to main memory 206 , from which processor 204 retrieves and executes the instructions.
- the instructions received by main memory 206 may optionally be stored on storage device 210 either before or after execution by processor 204 .
- Computer system 200 also includes a communication interface 218 coupled to bus 202 .
- Communication interface 218 provides a two-way data communication coupling to a network link 220 that is connected to a local network 222 .
- communication interface 218 may be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line.
- ISDN integrated services digital network
- communication interface 218 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN.
- LAN local area network
- Wireless links may also be implemented.
- communication interface 218 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
- Network link 220 typically provides data communication through one or more networks to other data devices.
- network link 220 may provide a connection through local network 222 to a host computer 224 or to data equipment operated by an Internet Service Provider (ISP) 226 .
- ISP 226 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the “Internet” 228 .
- Internet 228 uses electrical, electromagnetic or optical signals that carry digital data streams.
- the signals through the various networks and the signals on network link 220 and through communication interface 218 which carry the digital data to and from computer system 200 , are example forms of transmission media.
- Computer system 200 can send messages and receive data, including program code, through the network(s), network link 220 and communication interface 218 .
- a server 230 might transmit a requested code for an application program through Internet 228 , ISP 226 , local network 222 and communication interface 218 .
- the received code may be executed by processor 204 as it is received, and/or stored in storage device 210 , or other non-volatile storage for later execution.
Abstract
Description
- The present invention relates to services that allow users to comment on items and, more specifically, to techniques for helping each user to consume the user comments in which the user is personally interested.
- Recent years have seen rapid growth in user-generated opinions online. User-generated opinions take many forms. For example, one common form of user-generated opinions is user reviews. It is common for popular items to receive an unmanageably large number of user reviews. For example, on a book-selling website, a best-selling book may receive over 1000 reviews. Similarly, on a service that allows users to review restaurants, a popular restaurant can garner over 1000 reviews.
- Another common form of user-generated opinions comes in the form of user comments on blogs or news articles. Similar to reviewed items, news articles on popular topics may receive an unwieldy number of comments. For example, during the short period of time for which a major event is active, news stories on one single event can easily attract over ten thousand comments on popular online news sites.
- Reviews and news/blog commentary are merely two examples of user-generated comments. As used herein, the term “user-generated comments” refers to any content, provided by users for online publication, in relation to subject matter that is published or being discussed online. The subject matter at which the user-generated comments are directed may include, but is not limited to, products, songs, movies, news articles, discussion topics, sports teams, services, etc.
- Frequently, user-generated comments are published in conjunction with the subject matter to which the user-generated comments relate (the “target subject matter”). For example, the same webpage that has a news article may also include user comments related to the news article. Though entered in relation to a particular target subject matter, user-generated comments often do not actually express opinions about the target subject matter. For example, a user comment entered in relation to a news article may not actually have anything to do with the topic of the news article.
- Given the vast quantity of user-generated comments that may be generated for a target subject matter, it important to present user-generated comments in a manner that allows them to be easily consumed. One approach to facilitating the consumption of user-generated comments is to generate summaries of the user-generated comments. Review summarization may involve, for example, (a) automatically or manually identifying ratable aspects, and (b) presenting overall sentiment polarity for each aspect.
- Another technique for assisting user consumption of user-generated comments involves predicting the overall helpfulness of reviews in the hope of promoting those with better quality, where helpfulness is usually defined as some function over the percentage of users who found the review to be helpful. Both summarization and using a helpfulness rating focus on distilling subjective information that may be interesting to an average user.
- However, whether opinion consumers are looking for quality information or just wondering what other people think, each may have different purposes or preferences that are not well represented by a generic average user. In light of the foregoing, it is desirable to provide techniques that allow users to more easily consume the user-generated comments in which they are personally interested, without having to wade through a potentially vast ocean of user-generated comments that they would find less interesting.
- The approaches described in this section are approaches that could be pursued, but not necessarily approaches that have been previously conceived or pursued. Therefore, unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section.
- In the drawings:
-
FIG. 1 is a block diagram that illustrates how comments for the same article are presented in a different manner to three different users, according to an embodiment of the invention; and -
FIG. 2 is a block diagram of a computer system upon which embodiments of the invention may be implemented. - In the following description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent, however, that the present invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form in order to avoid unnecessarily obscuring the present invention.
- Techniques are described herein for facilitating the consumption of user-generated comments by determining which comments will be of most interest to each individual user. Once the comments that will be of most interest to a particular user are determined, the user-generated comments are presented to that user in a manner that reflects that user's predicted interest. For example, from 1000 reviews of a movie, each user may be presented with the 20 reviews that are predicted to be of most interest to the user. Because the predictions are personalized, different users are presented with different sets of 20 reviews, all for the same movie.
- As another example, all users may be presented the same 1000 reviews, but the reviews may be ordered based on predictions of how interested each individual user would be in each review. Instead of or in addition to filtering and ranking user-generated comments based on each user's predicted interest, the per-individual interest predictions may affect the display of user-generated comments in other ways, such as showing the reviews that are predicted to be of higher interest in different colors, highlighting, or using a larger font size. The layout of the interface presented to a user may also reflect user-specific information. For example, a user that is a frequent commenter may be provided an interface with a more prominent control for submitting comments, while a user that tends to skim through comments may be provided an interface that includes a greater number of comments.
- According to one embodiment, summarization of comments is also performed based on user-specific interest scores. For example, a user may be presented with summaries or aggregate ratings of only those comments that exceed a certain threshold of interest score for the user. Similarly, summaries may be separately derived and displayed for comments with interest scores above a threshold, and for comments with interest scores below the threshold. Those comments that are selected for display to a user may also include a first set of comments that are selected because they have high interest scores, and another set that are selected because they have low interest scores.
- A variety of factors may be used to predict, automatically, the interest each individual user would have in each user-generated comment. For example, interest predictions for a user may be based on the user's prior rating of comments, the ratings made by other users that are similar to the user, the textual content of comments, the textual content of the target subject matter, user-generated tags that have been supplied for the target subject matter, user-generated tags that have been supplied for comments, the degree to which comments are related to the subjects which they target, various types of profile and/or demographic information about the user, the user's social network connections, the authors of the comments, the author of the target subject matter, the user's propensity to comment, etc.
- According to one embodiment, rather than display user-generated comments for a target subject matter in the order in which the comments were made, or in a manner that reflects the interest of the average user, a system is provided for recommending user-generated comments to users in a user-specific manner. For example, many user-generated comment environments allow user to mark “like” or “dislike” over existing user-generated comments. A recommendation system may learn from each user's past preferences so that when a user is reading a news article, the user-generated comments for that article may be automatically ranked according to the likelihood of them being liked by this user. Such a system may be used directly to create personalized presentation of user-generated comments, as well as enabling down-stream applications, such as personalized summarization.
- Referring to
FIG. 1 , it illustrates displays that may result by implementing a personalized comment recommendation system, according to an embodiment of the invention. For the purpose of explanation, assume that three users (user1, user2 and user3) request to view thesame news article 100 at the same time. In response to the requests, a comment recommendation engine (not shown) determines user-specific interest scores for the comments associated with the article. Based on the user-specific interest scores, the comment recommendation engine determines which comments should be included on the webpage that is returned to each of the three users, and the order in which the comments are presented. - In the example illustrated in
FIG. 1 , the same comments were selected for user1 and user2, but the order in which the comments are presented differs based on the differences in the interest scores that those comments produced relative to user1 and user2. The comments that are selected and displayed to user3, on the other hand, include many comments that were not displayed to user1 and user2, and are missing some of the comments that were displayed to user1 and user2. -
FIG. 1 is merely one example of how the display of comments, from the comment pool of the same target subject matter, may differ from user to user based on user-specific interest scores generated for the comments. In alternative embodiments, the difference in interest scores of the comments may be reflected in other ways, such as the font size of the comments, the color of the comments, the amount of text shown in the initial display of the comments (where more text is initially shown for comments that are predicted to be of higher interest), etc. - A recommendation system for user-generated comments differs in a variety of ways from a system that recommends target subject matter, such as articles, to users. Specifically, recommending articles is largely about identifying the topics of interest to a given user, and it is conceivable that unigram representation of full-length articles can reasonably capture that information. In contrast, most user-generated comments for an article a user is reading are already of interest to that user topically. Which ones the user like may depend on several non-topical aspects of the text, such as: whether the user agrees with the viewpoint expressed in the user-generated comment, whether the user-generated comment is convincing and well-written, etc. In addition, user-generated comments are typically much shorter than full length articles, so there is generally less content upon which to base any recommendations.
- According to one embodiment, the difficulty in analyzing the textual information in user-generated comments can be alleviated by taking into account additional contextual information, such as author identities. If between a pair of users, one consistently likes or dislikes the other, then at least for the heavy users, this authorship information in itself could be adequate basis to determine whether a particular comment provided by one of the users would be of interest to the other user.
- According to one embodiment, multiple sources of information are used for the task of recommending user-generated comments. For example, authorship information is used in addition to textual information. Examples of various sources, and how information from those sources may be used to generate per-user interest scores for user-generated comments, are provided in greater detail hereafter.
- According to one embodiment, one factor used to automatically determine personalized interest scores is rater affinity to the user-generated comments. According to one embodiment, rater affinity is determined using a model that incorporates rater-comment interactions and rater-author interactions simultaneously in a principled fashion. The model also provides a seamless mechanism to transition from cold-start (where recommendations need to be made for users or items with no or few past ratings) to warm-start scenarios—with a large amount of data, it fits a per-rater (author) model; with increase in data sparsity, the model applies a small sample size correction through features (e.g. textual features). For one embodiment, the exact formula for such corrections in the presence of sparsity is based on parameter estimates that are obtained by applying an EM algorithm to the training data.
- A model is described herein for generating personalized interest scores for user-generated comments, according to an embodiment of the invention. This model is merely one example of how personalized interest scores may be generated, and the techniques described herein are not limited to any particular model, not any particular set of factors used by the model.
- For the purpose of describing the model, yij denotes the rating that user i, called the rater, gives to user-generated comment j. Because suffix i is used to denote a rater and suffix j to denote a user-generated comment, xi (of dimension pu) and xj (of dimension pc) denote feature vectors of user i and user-generated comment j, respectively. For example, xi can be the bag of words representation (a sparse vector) inferred through text analysis on user-generated comments voted positively by user i in the past, and xj can be the bag of words representation for user-generated comment j. In addition, a(j) is used to denote the author of user-generated comment j, and use μij to denote the mean rating by rater i on user-generated comment j, i.e., μij=E(yij). μij cannot be estimated empirically since each user i usually rates a user-generated comment j at most once.
- According to one embodiment, a generalized linear model framework is used (McCullagh and Nelder, 1989) that assumes μij (or some monotone function h of μij) is an additive function of:
-
- (1) the rater bias i of user i since some users may have a tendency of rating user-generated comments more positively or negatively than others,
- (2) popularity j of user-generated comment j, which could reflect the quality of the user-generated comment in this setting, and
- (3) the author reputation γa(j) of user a(j) since user-generated comments by a reputed author may in general get more positive ratings. Thus, the overall bias is αi+βj+γa(j).
- In addition to the bias, one embodiment includes terms that capture interactions among entities (raters, authors, user-generated comments). In addition, latent factors are attached to each rater, author and user-generated comment. These latent factors are finite dimensional Euclidean vectors that are unknown and estimated from the data. They provide a succinct representation of various aspects that are important to explain interaction among entities. In one embodiment, the following factors are used:
-
- (a) user factor vi of dimension rv(≧1) to model rater-author affinity,
- (b) user factor ui and user-generated comment factor cj of dimension ru(≧1) to model rater-comment affinity.
- Intuitively, each could represent viewpoints of users or user-generated comments along different dimensions.
- Affinity of rater i to user-generated comment j by author a(j) is captured by:
-
- (1) similarity between viewpoints of users i and a(j), measured by v′iva(j); and
- (2) similarity between the preferences of user i and the perspectives reflected in user-generated comment j, measured by u′icj.
- The overall interaction is v′iva(j)+u′icj. Then, the mean rating μij or more precisely h(μij), is modeled as the sum of bias and interaction terms. Mathematically, it is assumed that:
-
y ij ˜N(μij,σy 2) or Bernoulli(μij) -
h(μij)=αi+βj+γa(j) +v′ i v a(j) +u′ i c j - This equation shall be referred to hereafter as Equation 1.
- For numeric ratings, the Gaussian distribution denoted by N(mean, var) is used. For binary ratings, the Bernoulli distribution is used. For Gaussian, h(μij)=μij, and for Bernoulli, it is assumed that:
-
- which is the commonly used logistic transformation.
- The full model specified above is denoted as vv+uc since both user-user interaction v′iva(j) and user-user-generated comment interaction u′icj are modeled at the same time.
- Latent factors: To estimate latent factors in Equation 1, a maximum likelihood estimation (MLE) approach does not work well because a large fraction of entities have small sample size. For instance, if a user-generated comment is rated only by one user and ru>1, then the model is clearly overparametrized and the MLE of the user-generated comment factor would tend to learn idiosyncrasies in the training data.
- Hence, in one embodiment, constraints are imposed on the factors to obtain estimates that generalize well on unseen data. A Bayesian framework may be used, where such constraints are imposed through prior distributions.
- Priors that provide a good backoff estimate are needed when interacting entities have small sample sizes. For instance, to estimate latent factors of a user with little data, a backoff estimate that is obtained by pooling data across users with same user features is used. Such a pooling is performed through regression, the mathematical specification is given below.
-
αi ˜N(g′x i,σα 2),u i ˜N(Gx i,σu 2), -
βj ˜N(d′x j,σβ 2),c j ˜N(Dx j,σc 2), -
γa(j) ˜N(0,σγ 2),v i ˜N(0,σv 2), - where gp
u ×1 and dpu ×1 are regression weight vectors, and Gru ×pu and Dru ×pu are regression weight matrices. These regression weights are learnt from data and provide the backoff estimate. Take the prior distribution of ui for example. The prior can be rewritten as ui=Gxi+δi, where δi˜N(0, σu 2). - If user i has no rating in the training data, ui will be predicted as the prior mean (backoff) Gxi, a linear projection from the feature vector xi through matrix G learnt from data. This projection can be thought of as a multivariate linear regression problem with weight matrix G, one weight vector per dimension of ui. However, if user i has many ratings in the training data, the per-user residual i that is not captured by the regression Gxi is estimated. For sample sizes in between these two extremes, the per user residual estimate is “shrunk” toward zero, where the amount of shrinkage depends on the sample size, past user ratings, variability in ratings on user-generated comments rated by the user, and the value of variance components σ2
− s. - The full model (vv+uc) includes several existing models explored in collaborative filtering and social networks as special cases.
- The matrix factorization model: This model assumes the mean rating of user i on item j is given by h(μij)=αi+
β j+u′icj, and the mean of the prior distributions on αi, βj, ui, cj are zero, i.e., g=d=G=D=0: Recent work clearly illustrates that this method obtains better predictive accuracy than classical collaborative filtering techniques based on item-item similarity (Bell et al. (2007)). - The uc model: This is also a matrix factorization model but with priors based on regressions (i.e., non-zero g; d; G; D). It provides a mechanism to deal with both cold and warm-start scenarios in recommender applications (Agarwal and Chen (2009)).
-
- The vv model: This model assumes h(μij)=αi+γa(j)+v′iva(j). It was first proposed by Hoff (2005) to model interactions in social networks. The model was fitted to small datasets (at most a few hundred nodes) and the goal was to test certain hypotheses on social behavior, out-of-sample prediction was not considered.
- The low-rank bilinear regression model: Here, h(μij)=g′xi+d′xj+x′iG′Dxj.
- This is a regression model purely based on features with no per user or per-user-generated comment latent factors. In a more general form, x′iG′Dxj can be written as x′iAxj, where is the matrix of regression weights (Chu and Park, 2009). However, since xi and xj are typically high dimensional, A can be a large matrix that needs to be learnt from data. To reduce dimensionality, one can decompose A as A=G′D, where the number of rows in D and G are small. Thus, instead of learning A, a low-rank approximation of A is learned. This ensures scalability and provides an attractive method to avoid over-fitting.
- According to one embodiment, model fitting for the example model described above is based on the expectation-maximization (EM) algorithm (Dempster et al., 1977). For the purpose of explanation, a sketch of the algorithm for the Gaussian case is provided. The logistic model can be fitted along the same lines by using a variational approximation (see Agarwal and Chen (2009)).
- Let Y={yij} denote the set of the observed ratings. In the EM parlance, this is “incomplete” data that gets augmented with the latent factors Θ={ui, vi, cj} to obtain the “complete” data. The goal of the EM algorithm is to find the parameter η=(g, d, G, D, σα 2, σβ 2, σu 2, σv 2, σy 2) that maximizes the “incomplete” data likelihood Pr(Y|η)=∫Pr(Y,Θ|η)dΘ− that is obtained after marginalization (taking expectation) over the distribution of Θ. Since such marginalization is not available in closed form for our model, the EM algorithm is used.
- EM algorithm: The complete data log-likelihood l(η; Y, Θ) for the full model in the Gaussian case (where h(μij)=μij) is given by
-
- where ru is the dimension of factors ui and cj, and rv is the dimension of vi. Let η(t) denote the estimated parameter setting at the tth iteration. The EM algorithm iterates through the following two steps until convergence.
- E-step: ft(η)=EΘ[l(η; Y, Θ)|η(t)] as a function of η, where the expectation is taken over the posterior distribution of (Θ|η(t), Y).
- Note that here η is the input variable of function ft, but η(t) consists of known quantities (determined in the previous iteration).
- M-step: Find the η that maximizes the expectation computed in the E-step.
-
- Since the expectation in the E-step is not available in a closed form, a Gibbs sampler is used to compute the Monte Carlo expectation (Booth and Hobert, 1999). The Gibbs sampler repeats the following procedure L times. It samples αi, γi, βj, ui, vj and cj sequentially one at a time by sampling from the corresponding full conditional distributions. The full conditional distributions are all Gaussian, hence they are easy to sample. Once a Monte Carlo expectation is calculated from the samples, an updated estimate of η is obtained in the M-step. The optimization of variance components σ2 s in the M-step is available in closed form, the regression parameters are estimated through off-the-shelf linear regression routines. The posterior distribution of latent factors for known η is multi-modal, and the Monte Carlo based EM method tends to outperform other optimization methods like gradient descent in terms of predictive accuracy.
- The example model described above may be applied in many contexts to generate per-user-per-comment interest scores, and to present user-generated comments in a manner that is based on those interest scores. For example, the model may be applied in a situation where users read and comment on articles (such as news articles, blogs posts, status updates, event announcements, etc.), and have a mechanism for rating the comments. Information about how users actually rated the comments may be collected and used as a training set. Specifically, a portion of the collected data may be used for training, a portion for tuning, and a portion for testing the accuracy of the model.
- To obtain comment-specific features, all comments may be tokenized, lower-cased, with stopwords and punctuations removed. Further, the tokens may be filtered so that only the N most frequently used tokens are considered (where N may be, for example, 10,000). According to one embodiment, a rater feature vector is created by summing over the feature vectors of all comments rated positively by the rater.
- Various methods may be used to apply the example model to produce per-user-per-comment interest scores. For example, various embodiments may use any one or any combination of the full model vv+uc, as well as the three main special cases, vv, uc, and bilinear. The dimensions of vi, ui and cj (i.e., rv and ru), and the rank of bilinear are selected to obtain the best AUC on the tuning set. In one particular implementation, rv=2; ru=3 and rank of bilinear is 3. In addition, the following baseline methods may be used to predict per-user preferences in isolation, primarily based on textual information.
- Cosine similarity (cos): x′ixj. This is simply based on how similar a new comment j is to the comments rater i has liked in the past.
- Per-user SVM (svm): For each rater, train a support vector machine (SVM) classifier using only comments (xj) rated by that user.
- Per-user Naive Bayes (nb): For each rater, train a Naive Bayes classifier using only comments (xj) rated by that user.
- SVMs typically yield the best performance on text classification tasks. A Naive Bayes classifier can be more robust over shorter text spans common in user comments given the high variance.
- The example model described above uses various factors to determine per-user-per-comment interest scores. However, the factors used by the example model are merely some of the virtually limitless factors that may be used to determine how interested a specific user would be in each specific user-generated comment. A non-exhaustive list of factors that may be used individually or in any combination to determine individualized interest scores for user-generated comments for a particular reader includes:
-
- comment-specific features
- textual features of the comments
- tags applied to the comments
- age of the comments
- length of the comments
- time of day at which comments were submitted
- rating of this comment by other readers
- similarity between text of comments and text of target subject matter
- similarity between tags applied to comments and tags applied to target subject matter
- author-specific features
- prior ratings of author's comments by all readers
- prior ratings of author's comments by this reader
- profile of author (e.g. age, location, gender, political affiliation, religion, group memberships, etc.)
- degrees of separation between author and reader in a social network
- reader-specific features
- profile of the reader (e.g. age, location, gender, political affiliation, religion, group memberships, etc.)
- prior comment ratings by reader
- prior comment ratings by readers that are determined to be similar to the reader
- prior comment ratings by all readers
- confidence level of interest scores generated for this reader (may be low for readers for which little prior data is available)
- prior online behavior of reader outside comment rating context (e.g. web pages the reader has visited, search queries the reader has submitted, etc.)
- environment-specific features
- time of day that user-generated comment recommendation is being generated
- nature of computing device being used by reader
- current geographic location of reader
- target-subject-matter-specific features
- number of comments target subject matter has received
- topic or category of target subject-matter
- textual features of target subject matter
- tags applied to the target subject matter
- comment-specific features
- As mentioned above, once interest scores have been determined for a particular user for a particular set of user-generated comments, the particular user is provided a presentation of the user-generated comments that is personalized based on the interest scores. The number of ways the presentation can be personalized based on the interest scores is virtually endless. Two relatively simple forms of personalization include selecting which comments to show based on the interest scores, and determining the ranking of the comments based on the interest scores. However, there are any number of other ways the display of the comments may be personalized instead of or in addition to selection and ranking. Examples of ways to personalize the presentation of comments include:
-
- personalized layout of the display that includes the comments
- a larger region of the display for listing comments for users that tend to browse comments
- a larger region of the display for entering a comment for users that frequently submit comments
- a larger region of the display for listing comments when the target subject matter is a topic of high interest to the user
- pop-ups for comments with exceptionally high scores (e.g. comments made by the user's “friends”)
- in-place annotations for comments with exceptionally high scores
- comments with exceptionally high scores shown in a different location than other comments
- personalized listing of comments
- comments ordered (ranked) by interest scores
- comments grouped by interest scores (e.g. high, medium, and low scoring comment groups)
- font, color, size, highlights, frame of comment varies based on interest scores
- comments with scores below a threshold are hidden
- personalized summarization of comments
- separate comment summaries for high-scoring, medium-scoring and low-scoring comments
- exclude from summaries all comments whose interest scores fall below a threshold
- personalized layout of the display that includes the comments
- According to one embodiment, the techniques described herein are implemented by one or more special-purpose computing devices. The special-purpose computing devices may be hard-wired to perform the techniques, or may include digital electronic devices such as one or more application-specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that are persistently programmed to perform the techniques, or may include one or more general purpose hardware processors programmed to perform the techniques pursuant to program instructions in firmware, memory, other storage, or a combination. Such special-purpose computing devices may also combine custom hard-wired logic, ASICs, or FPGAs with custom programming to accomplish the techniques. The special-purpose computing devices may be desktop computer systems, portable computer systems, handheld devices, networking devices or any other device that incorporates hard-wired and/or program logic to implement the techniques.
- For example,
FIG. 2 is a block diagram that illustrates acomputer system 200 upon which an embodiment of the invention may be implemented.Computer system 200 includes abus 202 or other communication mechanism for communicating information, and ahardware processor 204 coupled withbus 202 for processing information.Hardware processor 204 may be, for example, a general purpose microprocessor. -
Computer system 200 also includes amain memory 206, such as a random access memory (RAM) or other dynamic storage device, coupled tobus 202 for storing information and instructions to be executed byprocessor 204.Main memory 206 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed byprocessor 204. Such instructions, when stored in non-transitory storage media accessible toprocessor 204, rendercomputer system 200 into a special-purpose machine that is customized to perform the operations specified in the instructions. -
Computer system 200 further includes a read only memory (ROM) 208 or other static storage device coupled tobus 202 for storing static information and instructions forprocessor 204. Astorage device 210, such as a magnetic disk or optical disk, is provided and coupled tobus 202 for storing information and instructions. -
Computer system 200 may be coupled viabus 202 to adisplay 212, such as a cathode ray tube (CRT), for displaying information to a computer user. Aninput device 214, including alphanumeric and other keys, is coupled tobus 202 for communicating information and command selections toprocessor 204. Another type of user input device iscursor control 216, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections toprocessor 204 and for controlling cursor movement ondisplay 212. This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the device to specify positions in a plane. -
Computer system 200 may implement the techniques described herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware and/or program logic which in combination with the computer system causes orprograms computer system 200 to be a special-purpose machine. According to one embodiment, the techniques herein are performed bycomputer system 200 in response toprocessor 204 executing one or more sequences of one or more instructions contained inmain memory 206. Such instructions may be read intomain memory 206 from another storage medium, such asstorage device 210. Execution of the sequences of instructions contained inmain memory 206 causesprocessor 204 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions. - The term “storage media” as used herein refers to any non-transitory media that store data and/or instructions that cause a machine to operation in a specific fashion. Such storage media may comprise non-volatile media and/or volatile media. Non-volatile media includes, for example, optical or magnetic disks, such as
storage device 210. Volatile media includes dynamic memory, such asmain memory 206. Common forms of storage media include, for example, a floppy disk, a flexible disk, hard disk, solid state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge. - Storage media is distinct from but may be used in conjunction with transmission media. Transmission media participates in transferring information between storage media. For example, transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise
bus 202. Transmission media can also take the form of acoustic or light waves, such as those generated during radio-wave and infra-red data communications. - Various forms of media may be involved in carrying one or more sequences of one or more instructions to
processor 204 for execution. For example, the instructions may initially be carried on a magnetic disk or solid state drive of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local tocomputer system 200 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal. An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data onbus 202.Bus 202 carries the data tomain memory 206, from whichprocessor 204 retrieves and executes the instructions. The instructions received bymain memory 206 may optionally be stored onstorage device 210 either before or after execution byprocessor 204. -
Computer system 200 also includes acommunication interface 218 coupled tobus 202.Communication interface 218 provides a two-way data communication coupling to anetwork link 220 that is connected to alocal network 222. For example,communication interface 218 may be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example,communication interface 218 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN. Wireless links may also be implemented. In any such implementation,communication interface 218 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information. - Network link 220 typically provides data communication through one or more networks to other data devices. For example,
network link 220 may provide a connection throughlocal network 222 to ahost computer 224 or to data equipment operated by an Internet Service Provider (ISP) 226.ISP 226 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the “Internet” 228.Local network 222 andInternet 228 both use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals onnetwork link 220 and throughcommunication interface 218, which carry the digital data to and fromcomputer system 200, are example forms of transmission media. -
Computer system 200 can send messages and receive data, including program code, through the network(s),network link 220 andcommunication interface 218. In the Internet example, aserver 230 might transmit a requested code for an application program throughInternet 228,ISP 226,local network 222 andcommunication interface 218. - The received code may be executed by
processor 204 as it is received, and/or stored instorage device 210, or other non-volatile storage for later execution. - In the foregoing specification, embodiments of the invention have been described with reference to numerous specific details that may vary from implementation to implementation. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the invention, and what is intended by the applicants to be the scope of the invention, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent correction.
Claims (20)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/364,369 US20130204833A1 (en) | 2012-02-02 | 2012-02-02 | Personalized recommendation of user comments |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/364,369 US20130204833A1 (en) | 2012-02-02 | 2012-02-02 | Personalized recommendation of user comments |
Publications (1)
Publication Number | Publication Date |
---|---|
US20130204833A1 true US20130204833A1 (en) | 2013-08-08 |
Family
ID=48903806
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/364,369 Abandoned US20130204833A1 (en) | 2012-02-02 | 2012-02-02 | Personalized recommendation of user comments |
Country Status (1)
Country | Link |
---|---|
US (1) | US20130204833A1 (en) |
Cited By (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130318099A1 (en) * | 2012-05-25 | 2013-11-28 | Dwango Co., Ltd. | Comment distribution system, and a method and a program for operating the comment distribution system |
US20140067975A1 (en) * | 2012-08-31 | 2014-03-06 | International Business Machines Corporation | Processing messages |
US20140149328A1 (en) * | 2012-11-28 | 2014-05-29 | Christian Posse | Evaluation of a recommender |
US20140164365A1 (en) * | 2012-12-11 | 2014-06-12 | Facebook, Inc. | Selection and presentation of news stories identifying external content to social networking system users |
US20140195610A1 (en) * | 2013-01-08 | 2014-07-10 | Vicomi | System and method for organizing and designing comment |
US20140280095A1 (en) * | 2013-03-15 | 2014-09-18 | Nevada Funding Group Inc. | Systems, methods and apparatus for rating and filtering online content |
US20140372429A1 (en) * | 2013-06-14 | 2014-12-18 | Microsoft Corporation | Incorporating user usage of consumable content into recommendations |
US20150026192A1 (en) * | 2013-04-19 | 2015-01-22 | salesforce.com,inc. | Systems and methods for topic filter recommendation for online social environments |
US20150187024A1 (en) * | 2013-12-27 | 2015-07-02 | Telefonica Digital España, S.L.U. | System and Method for Socially Aware Recommendations Based on Implicit User Feedback |
US20150261867A1 (en) * | 2014-03-13 | 2015-09-17 | Rohit Singal | Method and system of managing cues for conversation engagement |
US9146906B1 (en) * | 2012-06-19 | 2015-09-29 | Google Inc. | Modifying a webpage display based on a referrer web address |
US9177065B1 (en) | 2012-02-09 | 2015-11-03 | Google Inc. | Quality score for posts in social networking services |
US9183259B1 (en) | 2012-01-13 | 2015-11-10 | Google Inc. | Selecting content based on social significance |
US9223835B1 (en) | 2012-01-24 | 2015-12-29 | Google Inc. | Ranking and ordering items in stream |
US9313082B1 (en) | 2011-10-07 | 2016-04-12 | Google Inc. | Promoting user interaction based on user activity in social networking services |
CN105554581A (en) * | 2015-12-11 | 2016-05-04 | 小米科技有限责任公司 | Method and device for bullet screen display |
US20160227285A1 (en) * | 2013-09-16 | 2016-08-04 | Thomson Licensing | Browsing videos by searching multiple user comments and overlaying those into the content |
US9411856B1 (en) * | 2012-10-01 | 2016-08-09 | Google Inc. | Overlay generation for sharing a website |
US9454519B1 (en) * | 2012-08-15 | 2016-09-27 | Google Inc. | Promotion and demotion of posts in social networking services |
US9607325B1 (en) * | 2012-07-16 | 2017-03-28 | Amazon Technologies, Inc. | Behavior-based item review system |
US20170124080A1 (en) * | 2015-10-30 | 2017-05-04 | At&T Intellectual Property I, L.P. | Method and apparatus for providing a recommendation for learning about an interest of a user |
US20170142046A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Identifying relevant content contained in message streams that appear to be irrelevant |
US20170169029A1 (en) * | 2015-12-15 | 2017-06-15 | Facebook, Inc. | Systems and methods for ranking comments based on information associated with comments |
US20170220935A1 (en) * | 2016-01-28 | 2017-08-03 | Linkedin Corporation | Member feature sets, group feature sets and trained coefficients for recommending relevant groups |
WO2017147785A1 (en) * | 2016-03-01 | 2017-09-08 | Microsoft Technology Licensing, Llc | Automated commentary for online content |
US9785625B1 (en) * | 2013-06-27 | 2017-10-10 | Google Inc. | Increasing comment visibility |
US9846836B2 (en) | 2014-06-13 | 2017-12-19 | Microsoft Technology Licensing, Llc | Modeling interestingness with deep neural networks |
US20170373999A1 (en) * | 2016-06-27 | 2017-12-28 | International Business Machines Corporation | Familiarity-based involvement on an online group conversation |
CN108062375A (en) * | 2017-12-12 | 2018-05-22 | 百度在线网络技术(北京)有限公司 | A kind of processing method, device, terminal and the storage medium of user's portrait |
US20180165379A1 (en) * | 2016-12-08 | 2018-06-14 | Accenture Global Solutions Limited | Platform for supporting multiple virtual agent applications |
US20180181662A1 (en) * | 2016-12-28 | 2018-06-28 | Facebook, Inc. | Selecting User Posts Related to Trending Topics on Online Social Networks |
US10217058B2 (en) | 2014-01-30 | 2019-02-26 | Microsoft Technology Licensing, Llc | Predicting interesting things and concepts in content |
US20190197122A1 (en) * | 2017-12-27 | 2019-06-27 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and device for generating review article of hot news, and terminal device |
CN110162621A (en) * | 2019-02-22 | 2019-08-23 | 腾讯科技(深圳)有限公司 | Disaggregated model training method, abnormal comment detection method, device and equipment |
US10595094B2 (en) | 2013-09-10 | 2020-03-17 | Opentv, Inc. | Systems and methods of displaying content |
CN111428145A (en) * | 2020-03-19 | 2020-07-17 | 重庆邮电大学 | Recommendation method and system fusing tag data and naive Bayesian classification |
CN112632377A (en) * | 2020-12-21 | 2021-04-09 | 西北大学 | Recommendation method based on user comment emotion analysis and matrix decomposition |
CN112785331A (en) * | 2021-01-07 | 2021-05-11 | 之江实验室 | Injection attack resistant robust recommendation method and system combining evaluation text |
US20210160209A1 (en) * | 2013-02-08 | 2021-05-27 | Google Llc | Methods, systems, and media for presenting comments based on correlation with content |
CN113127628A (en) * | 2021-04-23 | 2021-07-16 | 北京达佳互联信息技术有限公司 | Method, device, equipment and computer-readable storage medium for generating comments |
JP2021174552A (en) * | 2020-04-27 | 2021-11-01 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Alignment method of comment, device, apparatus and computer storage medium |
US11216742B2 (en) | 2019-03-04 | 2022-01-04 | Iocurrents, Inc. | Data compression and communication using machine learning |
US11556335B1 (en) | 2021-09-14 | 2023-01-17 | International Business Machines Corporation | Annotating program code |
US11593444B2 (en) | 2010-09-07 | 2023-02-28 | Opentv, Inc. | Collecting data from different sources |
US11741110B2 (en) | 2012-08-31 | 2023-08-29 | Google Llc | Aiding discovery of program content by providing deeplinks into most interesting moments via social media |
CN117094856A (en) * | 2023-08-24 | 2023-11-21 | 哈尔滨工业大学 | Prediction method for user evaluation behavior after embedding OTA website based on panel logic model |
Citations (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010021914A1 (en) * | 1998-09-18 | 2001-09-13 | Jacobi Jennifer A. | Personalized recommendations of items represented within a database |
US6321221B1 (en) * | 1998-07-17 | 2001-11-20 | Net Perceptions, Inc. | System, method and article of manufacture for increasing the user value of recommendations |
CA2425217A1 (en) * | 2002-04-12 | 2003-10-12 | Eric Boyd | Method and system for single-action personalized recommendation and display of internet content |
US20040098313A1 (en) * | 2002-11-19 | 2004-05-20 | Ashish Agrawal | Detection of fraudulent associate-based transactions |
US20040172267A1 (en) * | 2002-08-19 | 2004-09-02 | Jayendu Patel | Statistical personalized recommendation system |
US7158986B1 (en) * | 1999-07-27 | 2007-01-02 | Mailfrontier, Inc. A Wholly Owned Subsidiary Of Sonicwall, Inc. | Method and system providing user with personalized recommendations by electronic-mail based upon the determined interests of the user pertain to the theme and concepts of the categorized document |
US20080133488A1 (en) * | 2006-11-22 | 2008-06-05 | Nagaraju Bandaru | Method and system for analyzing user-generated content |
US20090019488A1 (en) * | 2007-07-10 | 2009-01-15 | Verizon Data Services, Inc. | System and method for providing personal content recommendations |
US20090083314A1 (en) * | 2003-10-24 | 2009-03-26 | Enrico Maim | Method of Manipulating Information Objects and of Accessing Such Objects in a Computer Environment |
US7526464B2 (en) * | 2003-11-28 | 2009-04-28 | Manyworlds, Inc. | Adaptive fuzzy network system and method |
US20090125499A1 (en) * | 2007-11-09 | 2009-05-14 | Microsoft Corporation | Machine-moderated mobile social networking for managing queries |
US20090210246A1 (en) * | 2002-08-19 | 2009-08-20 | Choicestream, Inc. | Statistical personalized recommendation system |
US20090254971A1 (en) * | 1999-10-27 | 2009-10-08 | Pinpoint, Incorporated | Secure data interchange |
US20090282019A1 (en) * | 2008-05-12 | 2009-11-12 | Threeall, Inc. | Sentiment Extraction from Consumer Reviews for Providing Product Recommendations |
US20090313041A1 (en) * | 2002-12-10 | 2009-12-17 | Jeffrey Scott Eder | Personalized modeling system |
US20100057569A1 (en) * | 2008-08-29 | 2010-03-04 | Nathan Cantelmo | Advertising System for Internet Discussion Forums |
US20100106668A1 (en) * | 2008-10-17 | 2010-04-29 | Louis Hawthorne | System and method for providing community wisdom based on user profile |
US20100211568A1 (en) * | 2009-02-19 | 2010-08-19 | Wei Chu | Personalized recommendations on dynamic content |
US20100287033A1 (en) * | 2009-05-08 | 2010-11-11 | Comcast Interactive Media, Llc | Social Network Based Recommendation Method and System |
US20100306192A1 (en) * | 2009-05-28 | 2010-12-02 | Tip Top Technologies, Inc. | Method and system for a search engine for user generated content (ugc) |
US20100312464A1 (en) * | 2007-05-01 | 2010-12-09 | Chicke Fitzgerald | Advice engine delivering personalized search results and customized roadtrip plans |
US20100332283A1 (en) * | 2009-06-29 | 2010-12-30 | Apple Inc. | Social networking in shopping environments |
US20110004831A1 (en) * | 2009-03-04 | 2011-01-06 | Arieh Steinberg | Filtering Content in a Social Networking Service |
US20110113332A1 (en) * | 2008-06-25 | 2011-05-12 | At&T Intellectual Property I, L.P. | Apparatus and method for monitoring and control on a network |
US7958066B2 (en) * | 2007-11-02 | 2011-06-07 | Hunch Inc. | Interactive machine learning advice facility |
US20110138326A1 (en) * | 2009-12-04 | 2011-06-09 | At&T Intellectual Property I, L.P. | Apparatus and Method for Tagging Media Content and Managing Marketing |
US7966282B2 (en) * | 2007-11-02 | 2011-06-21 | Hunch Inc. | Interactive machine learning advice facility with contextual suggestions |
US20110179081A1 (en) * | 2010-01-19 | 2011-07-21 | Maksims Ovsjanikov | Personalized recommendation of a volatile item |
US20110258556A1 (en) * | 2010-04-16 | 2011-10-20 | Microsoft Corporation | Social home page |
US20120158516A1 (en) * | 2010-07-20 | 2012-06-21 | Wooten Iii William Eric | System and method for context, community and user based determinatiion, targeting and display of relevant sales channel content |
US20120303415A1 (en) * | 2011-05-25 | 2012-11-29 | Ari Edelson | System and method of providing recommendations |
US8359285B1 (en) * | 2009-09-18 | 2013-01-22 | Amazon Technologies, Inc. | Generating item recommendations |
-
2012
- 2012-02-02 US US13/364,369 patent/US20130204833A1/en not_active Abandoned
Patent Citations (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6321221B1 (en) * | 1998-07-17 | 2001-11-20 | Net Perceptions, Inc. | System, method and article of manufacture for increasing the user value of recommendations |
US20010021914A1 (en) * | 1998-09-18 | 2001-09-13 | Jacobi Jennifer A. | Personalized recommendations of items represented within a database |
US7113917B2 (en) * | 1998-09-18 | 2006-09-26 | Amazon.Com, Inc. | Personalized recommendations of items represented within a database |
US7158986B1 (en) * | 1999-07-27 | 2007-01-02 | Mailfrontier, Inc. A Wholly Owned Subsidiary Of Sonicwall, Inc. | Method and system providing user with personalized recommendations by electronic-mail based upon the determined interests of the user pertain to the theme and concepts of the categorized document |
US20090254971A1 (en) * | 1999-10-27 | 2009-10-08 | Pinpoint, Incorporated | Secure data interchange |
US8078615B2 (en) * | 2002-04-12 | 2011-12-13 | Stumbleupon, Inc. | Method and system for single-action personalized recommendation and display of internet content |
CA2425217A1 (en) * | 2002-04-12 | 2003-10-12 | Eric Boyd | Method and system for single-action personalized recommendation and display of internet content |
US20030195884A1 (en) * | 2002-04-12 | 2003-10-16 | Eric Boyd | Method and system for single-action personalized recommendation and display of internet content |
US20040172267A1 (en) * | 2002-08-19 | 2004-09-02 | Jayendu Patel | Statistical personalized recommendation system |
US20060259344A1 (en) * | 2002-08-19 | 2006-11-16 | Choicestream, A Delaware Corporation | Statistical personalized recommendation system |
US20090210246A1 (en) * | 2002-08-19 | 2009-08-20 | Choicestream, Inc. | Statistical personalized recommendation system |
US20040098313A1 (en) * | 2002-11-19 | 2004-05-20 | Ashish Agrawal | Detection of fraudulent associate-based transactions |
US20090313041A1 (en) * | 2002-12-10 | 2009-12-17 | Jeffrey Scott Eder | Personalized modeling system |
US20090083314A1 (en) * | 2003-10-24 | 2009-03-26 | Enrico Maim | Method of Manipulating Information Objects and of Accessing Such Objects in a Computer Environment |
US7526464B2 (en) * | 2003-11-28 | 2009-04-28 | Manyworlds, Inc. | Adaptive fuzzy network system and method |
US20080133488A1 (en) * | 2006-11-22 | 2008-06-05 | Nagaraju Bandaru | Method and system for analyzing user-generated content |
US20100312464A1 (en) * | 2007-05-01 | 2010-12-09 | Chicke Fitzgerald | Advice engine delivering personalized search results and customized roadtrip plans |
US20090019488A1 (en) * | 2007-07-10 | 2009-01-15 | Verizon Data Services, Inc. | System and method for providing personal content recommendations |
US7958066B2 (en) * | 2007-11-02 | 2011-06-07 | Hunch Inc. | Interactive machine learning advice facility |
US7966282B2 (en) * | 2007-11-02 | 2011-06-21 | Hunch Inc. | Interactive machine learning advice facility with contextual suggestions |
US8032480B2 (en) * | 2007-11-02 | 2011-10-04 | Hunch Inc. | Interactive computing advice facility with learning based on user feedback |
US8032481B2 (en) * | 2007-11-02 | 2011-10-04 | Hunch Inc. | Interactive computing advice facility that infers user profiles from social networking relationships |
US20090125499A1 (en) * | 2007-11-09 | 2009-05-14 | Microsoft Corporation | Machine-moderated mobile social networking for managing queries |
US20090282019A1 (en) * | 2008-05-12 | 2009-11-12 | Threeall, Inc. | Sentiment Extraction from Consumer Reviews for Providing Product Recommendations |
US20110113332A1 (en) * | 2008-06-25 | 2011-05-12 | At&T Intellectual Property I, L.P. | Apparatus and method for monitoring and control on a network |
US20100057569A1 (en) * | 2008-08-29 | 2010-03-04 | Nathan Cantelmo | Advertising System for Internet Discussion Forums |
US20100106668A1 (en) * | 2008-10-17 | 2010-04-29 | Louis Hawthorne | System and method for providing community wisdom based on user profile |
US20100211568A1 (en) * | 2009-02-19 | 2010-08-19 | Wei Chu | Personalized recommendations on dynamic content |
US20110004831A1 (en) * | 2009-03-04 | 2011-01-06 | Arieh Steinberg | Filtering Content in a Social Networking Service |
US20100287033A1 (en) * | 2009-05-08 | 2010-11-11 | Comcast Interactive Media, Llc | Social Network Based Recommendation Method and System |
US20100306192A1 (en) * | 2009-05-28 | 2010-12-02 | Tip Top Technologies, Inc. | Method and system for a search engine for user generated content (ugc) |
US20100332283A1 (en) * | 2009-06-29 | 2010-12-30 | Apple Inc. | Social networking in shopping environments |
US8359285B1 (en) * | 2009-09-18 | 2013-01-22 | Amazon Technologies, Inc. | Generating item recommendations |
US20110138326A1 (en) * | 2009-12-04 | 2011-06-09 | At&T Intellectual Property I, L.P. | Apparatus and Method for Tagging Media Content and Managing Marketing |
US20110179081A1 (en) * | 2010-01-19 | 2011-07-21 | Maksims Ovsjanikov | Personalized recommendation of a volatile item |
US20110258556A1 (en) * | 2010-04-16 | 2011-10-20 | Microsoft Corporation | Social home page |
US20120158516A1 (en) * | 2010-07-20 | 2012-06-21 | Wooten Iii William Eric | System and method for context, community and user based determinatiion, targeting and display of relevant sales channel content |
US20120303415A1 (en) * | 2011-05-25 | 2012-11-29 | Ari Edelson | System and method of providing recommendations |
Non-Patent Citations (6)
Title |
---|
Calegari et al., "Ontology-Based Information Behaviour to ImproveWeb Search," Future Internet 2010, 2, pp. 533-558. * |
Gauch et al., "User Profiles for Personalized Information Access," In P. Brusilovsky, A. Kobsa, and W. Nejdl (Eds.): The Adaptive Web, LNCS 4321, pp. 54 - 89, 2007. * |
Herlocker et al., "Evaluating Collaborative Filtering Recommender Systems," ACM Transactions on Information Systems, Vol. 22, No. 1, January 2004, Pages 5-53. * |
Li et al., "User comments for news recommendation in forum-based social media," Information Sciences 180 (2010), pp. 4929-4939. * |
Messenger te al., "Recommendations Based on User-generated Comments in Social Media," In: Proceedings, 2011 IEEE International Conference on Privacy, Security, Risk, and Trust, and IEEE International Conference on Social Computer, 9-11 Oct. 2011, pp. 505-508. * |
Sieg et al., "Improving the Effectiveness of Collaborative Recommendation with Ontology-Based User Profiles," In: Proceedings of HetRec'10, Barcelona, Spain, September 26, 2010. * |
Cited By (72)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11593444B2 (en) | 2010-09-07 | 2023-02-28 | Opentv, Inc. | Collecting data from different sources |
US9313082B1 (en) | 2011-10-07 | 2016-04-12 | Google Inc. | Promoting user interaction based on user activity in social networking services |
US9183259B1 (en) | 2012-01-13 | 2015-11-10 | Google Inc. | Selecting content based on social significance |
US9223835B1 (en) | 2012-01-24 | 2015-12-29 | Google Inc. | Ranking and ordering items in stream |
US10133765B1 (en) | 2012-02-09 | 2018-11-20 | Google Llc | Quality score for posts in social networking services |
US9177065B1 (en) | 2012-02-09 | 2015-11-03 | Google Inc. | Quality score for posts in social networking services |
US20130318099A1 (en) * | 2012-05-25 | 2013-11-28 | Dwango Co., Ltd. | Comment distribution system, and a method and a program for operating the comment distribution system |
US9606991B2 (en) * | 2012-05-25 | 2017-03-28 | Dwango Co., Ltd. | Comment distribution system, and a method and a program for operating the comment distribution system |
US9146906B1 (en) * | 2012-06-19 | 2015-09-29 | Google Inc. | Modifying a webpage display based on a referrer web address |
US9607325B1 (en) * | 2012-07-16 | 2017-03-28 | Amazon Technologies, Inc. | Behavior-based item review system |
US9454519B1 (en) * | 2012-08-15 | 2016-09-27 | Google Inc. | Promotion and demotion of posts in social networking services |
US20140067975A1 (en) * | 2012-08-31 | 2014-03-06 | International Business Machines Corporation | Processing messages |
US11741110B2 (en) | 2012-08-31 | 2023-08-29 | Google Llc | Aiding discovery of program content by providing deeplinks into most interesting moments via social media |
US9411856B1 (en) * | 2012-10-01 | 2016-08-09 | Google Inc. | Overlay generation for sharing a website |
US9361584B2 (en) | 2012-11-28 | 2016-06-07 | Linkedin Corporation | Recommender evaluation based on tokenized messages |
US9171257B2 (en) | 2012-11-28 | 2015-10-27 | Linkedin Corporation | Recommender evaluation based on tokenized messages |
US8959044B2 (en) * | 2012-11-28 | 2015-02-17 | Linkedin Corporation | Recommender evaluation based on tokenized messages |
US20140149328A1 (en) * | 2012-11-28 | 2014-05-29 | Christian Posse | Evaluation of a recommender |
US10037538B2 (en) * | 2012-12-11 | 2018-07-31 | Facebook, Inc. | Selection and presentation of news stories identifying external content to social networking system users |
US20140164365A1 (en) * | 2012-12-11 | 2014-06-12 | Facebook, Inc. | Selection and presentation of news stories identifying external content to social networking system users |
US20220358463A1 (en) * | 2013-01-08 | 2022-11-10 | Emm Patents Ltd. | System and method for organizing and designing comment |
US11436565B2 (en) * | 2013-01-08 | 2022-09-06 | Emm Patents Ltd. | System and method for organizing and designing comment |
US10776756B2 (en) * | 2013-01-08 | 2020-09-15 | Emm Patents Ltd. | System and method for organizing and designing comment |
US20140195610A1 (en) * | 2013-01-08 | 2014-07-10 | Vicomi | System and method for organizing and designing comment |
US11689491B2 (en) * | 2013-02-08 | 2023-06-27 | Google Llc | Methods, systems, and media for presenting comments based on correlation with content |
US20210160209A1 (en) * | 2013-02-08 | 2021-05-27 | Google Llc | Methods, systems, and media for presenting comments based on correlation with content |
US20140280095A1 (en) * | 2013-03-15 | 2014-09-18 | Nevada Funding Group Inc. | Systems, methods and apparatus for rating and filtering online content |
US20150026192A1 (en) * | 2013-04-19 | 2015-01-22 | salesforce.com,inc. | Systems and methods for topic filter recommendation for online social environments |
US11061973B2 (en) * | 2013-06-14 | 2021-07-13 | Microsoft Technology Licensing, Llc | Incorporating user usage of consumable content into recommendations |
US20140372429A1 (en) * | 2013-06-14 | 2014-12-18 | Microsoft Corporation | Incorporating user usage of consumable content into recommendations |
US9785625B1 (en) * | 2013-06-27 | 2017-10-10 | Google Inc. | Increasing comment visibility |
US11138368B1 (en) | 2013-06-27 | 2021-10-05 | Google Llc | Increasing comment visibility |
US10452772B1 (en) | 2013-06-27 | 2019-10-22 | Google Llc | Increasing comment visibility |
US10992995B2 (en) | 2013-09-10 | 2021-04-27 | Opentv, Inc. | Systems and methods of displaying content |
US11363342B2 (en) | 2013-09-10 | 2022-06-14 | Opentv, Inc. | Systems and methods of displaying content |
US11825171B2 (en) | 2013-09-10 | 2023-11-21 | Opentv, Inc. | Systems and methods of displaying content |
US10595094B2 (en) | 2013-09-10 | 2020-03-17 | Opentv, Inc. | Systems and methods of displaying content |
US20160227285A1 (en) * | 2013-09-16 | 2016-08-04 | Thomson Licensing | Browsing videos by searching multiple user comments and overlaying those into the content |
US20150187024A1 (en) * | 2013-12-27 | 2015-07-02 | Telefonica Digital España, S.L.U. | System and Method for Socially Aware Recommendations Based on Implicit User Feedback |
US10217058B2 (en) | 2014-01-30 | 2019-02-26 | Microsoft Technology Licensing, Llc | Predicting interesting things and concepts in content |
US20150261867A1 (en) * | 2014-03-13 | 2015-09-17 | Rohit Singal | Method and system of managing cues for conversation engagement |
US9846836B2 (en) | 2014-06-13 | 2017-12-19 | Microsoft Technology Licensing, Llc | Modeling interestingness with deep neural networks |
US10331679B2 (en) * | 2015-10-30 | 2019-06-25 | At&T Intellectual Property I, L.P. | Method and apparatus for providing a recommendation for learning about an interest of a user |
US20170124080A1 (en) * | 2015-10-30 | 2017-05-04 | At&T Intellectual Property I, L.P. | Method and apparatus for providing a recommendation for learning about an interest of a user |
US10129193B2 (en) * | 2015-11-17 | 2018-11-13 | International Business Machines Corporation | Identifying relevant content contained in message streams that appear to be irrelevant |
US20170142046A1 (en) * | 2015-11-17 | 2017-05-18 | International Business Machines Corporation | Identifying relevant content contained in message streams that appear to be irrelevant |
CN105554581A (en) * | 2015-12-11 | 2016-05-04 | 小米科技有限责任公司 | Method and device for bullet screen display |
US20170169029A1 (en) * | 2015-12-15 | 2017-06-15 | Facebook, Inc. | Systems and methods for ranking comments based on information associated with comments |
US20170220935A1 (en) * | 2016-01-28 | 2017-08-03 | Linkedin Corporation | Member feature sets, group feature sets and trained coefficients for recommending relevant groups |
US11922300B2 (en) | 2016-03-01 | 2024-03-05 | Microsoft Technology Licensing, Llc. | Automated commentary for online content |
WO2017147785A1 (en) * | 2016-03-01 | 2017-09-08 | Microsoft Technology Licensing, Llc | Automated commentary for online content |
US9973460B2 (en) * | 2016-06-27 | 2018-05-15 | International Business Machines Corporation | Familiarity-based involvement on an online group conversation |
US20170373999A1 (en) * | 2016-06-27 | 2017-12-28 | International Business Machines Corporation | Familiarity-based involvement on an online group conversation |
US20180165379A1 (en) * | 2016-12-08 | 2018-06-14 | Accenture Global Solutions Limited | Platform for supporting multiple virtual agent applications |
US11093307B2 (en) * | 2016-12-08 | 2021-08-17 | Accenture Global Solutions Limited | Platform for supporting multiple virtual agent applications |
US20180181662A1 (en) * | 2016-12-28 | 2018-06-28 | Facebook, Inc. | Selecting User Posts Related to Trending Topics on Online Social Networks |
US10535106B2 (en) * | 2016-12-28 | 2020-01-14 | Facebook, Inc. | Selecting user posts related to trending topics on online social networks |
CN108062375A (en) * | 2017-12-12 | 2018-05-22 | 百度在线网络技术(北京)有限公司 | A kind of processing method, device, terminal and the storage medium of user's portrait |
US20190197122A1 (en) * | 2017-12-27 | 2019-06-27 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and device for generating review article of hot news, and terminal device |
US10860811B2 (en) * | 2017-12-27 | 2020-12-08 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and device for generating review article of hot news, and terminal device |
CN110162621A (en) * | 2019-02-22 | 2019-08-23 | 腾讯科技(深圳)有限公司 | Disaggregated model training method, abnormal comment detection method, device and equipment |
US11216742B2 (en) | 2019-03-04 | 2022-01-04 | Iocurrents, Inc. | Data compression and communication using machine learning |
US11468355B2 (en) | 2019-03-04 | 2022-10-11 | Iocurrents, Inc. | Data compression and communication using machine learning |
CN111428145A (en) * | 2020-03-19 | 2020-07-17 | 重庆邮电大学 | Recommendation method and system fusing tag data and naive Bayesian classification |
US11514090B2 (en) | 2020-04-27 | 2022-11-29 | Baidu Online Network Technology (Beijing) Co., Ltd. | Comments-ordering method, apparatus, device and computer storage medium |
JP7222017B2 (en) | 2020-04-27 | 2023-02-14 | バイドゥ オンライン ネットワーク テクノロジー(ペキン) カンパニー リミテッド | Method for arranging comments, device, equipment and computer storage medium |
JP2021174552A (en) * | 2020-04-27 | 2021-11-01 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Alignment method of comment, device, apparatus and computer storage medium |
CN112632377A (en) * | 2020-12-21 | 2021-04-09 | 西北大学 | Recommendation method based on user comment emotion analysis and matrix decomposition |
CN112785331A (en) * | 2021-01-07 | 2021-05-11 | 之江实验室 | Injection attack resistant robust recommendation method and system combining evaluation text |
CN113127628A (en) * | 2021-04-23 | 2021-07-16 | 北京达佳互联信息技术有限公司 | Method, device, equipment and computer-readable storage medium for generating comments |
US11556335B1 (en) | 2021-09-14 | 2023-01-17 | International Business Machines Corporation | Annotating program code |
CN117094856A (en) * | 2023-08-24 | 2023-11-21 | 哈尔滨工业大学 | Prediction method for user evaluation behavior after embedding OTA website based on panel logic model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20130204833A1 (en) | Personalized recommendation of user comments | |
US10832219B2 (en) | Using feedback to create and modify candidate streams | |
Wei et al. | A hybrid approach for movie recommendation via tags and ratings | |
US20190392330A1 (en) | System and method for generating aspect-enhanced explainable description-based recommendations | |
Alahmadi et al. | ISTS: Implicit social trust and sentiment based approach to recommender systems | |
Ganu et al. | Improving the quality of predictions using textual information in online user reviews | |
Ge et al. | Cost-aware travel tour recommendation | |
US8909626B2 (en) | Determining user preference of items based on user ratings and user features | |
US9141966B2 (en) | Opinion aggregation system | |
US20150073931A1 (en) | Feature selection for recommender systems | |
Agarwal et al. | Personalized recommendation of user comments via factor models | |
Dash et al. | Personalized ranking of online reviews based on consumer preferences in product features | |
Ahmed et al. | Rating-based recommender system based on textual reviews using iot smart devices | |
Hong et al. | Latent space regularization for recommender systems | |
Benabbes et al. | Recommendation system issues, approaches and challenges based on user reviews | |
KR20190130410A (en) | Apparatus and method for recommending customized content for smart senior | |
Thomas et al. | A novel framework for an intelligent deep learning based product recommendation system using sentiment analysis (SA) | |
Al-Saffar et al. | Survey on Implicit Feedbacks Extraction based on Yelp Dataset using Collaborative Filtering | |
Mirzaeibonehkhater | Developing a dynamic recommendation system for personalizing educational content within an e-learning network | |
Patil et al. | A Comparison of Similarity Measures in an Online Book Recommendation System | |
Zafar Ali Khan et al. | Hybrid Collaborative Fusion Based Product Recommendation Exploiting Sentiments from Implicit and Explicit Reviews | |
US20170075519A1 (en) | Data Butler | |
Wang | Viewability prediction for display advertising | |
Maharani et al. | Dynamic aspect-based rating system and visualization | |
Albalawi | Toward a Real-Time Recommendation for Online Social Networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: YAHOO| INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:PANG, BO;CHEN, BEE-CHUNG;AGARWAL, DEEPAK K.;SIGNING DATES FROM 20120127 TO 20120201;REEL/FRAME:027641/0428 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: YAHOO HOLDINGS, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:YAHOO| INC.;REEL/FRAME:042963/0211 Effective date: 20170613 |
|
AS | Assignment |
Owner name: OATH INC., NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:YAHOO HOLDINGS, INC.;REEL/FRAME:045240/0310 Effective date: 20171231 |